{
  "$type": "site.standard.document",
  "bskyPostRef": {
    "cid": "bafyreibldf72lf6t56iuil3qoqtjxdwoug5oicg7nofxk7ys42g6lwliga",
    "uri": "at://did:plc:lk3jfj3zq4k4wxnk474axylu/app.bsky.feed.post/3mpl4zea6kf62"
  },
  "path": "/t/custom-gpt-actions-intermittently-fail-to-dispatch-actions-not-available-in-this-chat-session-nothing-reaches-our-server/1385448#post_1",
  "publishedAt": "2026-07-01T08:24:08.000Z",
  "site": "https://community.openai.com",
  "textContent": "Standard workspace (not FedRAMP), ChatGPT Pro, web.\n\nOur custom GPTs have OAuth-configured actions with a valid OpenAPI 3.1.0 schema. Intermittently, the GPT responds that “the required actions aren’t available in this chat session” and **no request reaches our backend** (confirmed via server logs — total silence, not an error). Minutes earlier the same GPT, same config, dispatched the same actions successfully. No changes on our side between working and failing runs.\n\nCritically, the **Action “Test” button in the GPT builder also fails to fire** on these actions — this bypasses the model, instructions, and schema interpretation entirely, so it is not a prompting or configuration issue on our end.\n\nVerified our side is healthy: direct `curl` to the endpoint returns correct responses (401 without token). The failure is in ChatGPT’s action-dispatch layer, not our server.\n\nMulti-action GPTs are hit hardest; single-action GPTs are more reliable. Intermittent and non-reproducible on identical input.",
  "title": "Custom GPT actions intermittently fail to dispatch — \"actions not available in this chat session,\" nothing reaches our server"
}